gpudiff the public record of change in GPU cloud pricing
Follow the diffs: RSS · Free API · Sponsor this site

llama-3.1-8b-instruct API price — 4 gateways compared

from $0.02 per million input tokens · 2.5× spread between gateways · updated hourly

Gateway$ in /MTok$ out /MTok ContextInput price historyModel ID
Novita$0.02$0.0516,384since 2026-08-20meta-llama/llama-3.1-8b-instruct
OpenRouter fees$0.05$0.08131,072meta-llama/llama-3.1-8b-instruct
Requesty$0.05$0.0516,384since 2026-08-20novita/meta-llama/llama-3.1-8b-instruct
Glama$0.05$0.08128,000since 2026-08-20meta/llama-3.1-8b-instruct

Fees beyond the token price

Changelog for llama-3.1-8b-instruct

llama-3.1-8b-instruct pricing FAQ

How much does llama-3.1-8b-instruct cost per million tokens?

The cheapest tracked gateway charges $0.02 per million input tokens and $0.05 per million output tokens (Novita). Prices refresh hourly.

Which gateway is cheapest for llama-3.1-8b-instruct?

Novita for input tokens and Novita for output tokens, among the 4 gateways we track.

Do llama-3.1-8b-instruct prices differ between gateways?

Yes — the most expensive tracked gateway charges 2.5× the cheapest for input tokens. Identical model, identical tokens, different bill.

← All LLM prices · API